01Module 01 - Scientific Python Stack OverviewNumPy, Pandas, SciPy, Matplotlib, scikit-learn, PyTorch, and JAX - the complete Python stack for AI/ML engineering.02NumPy InternalsNumPy memory layout, strides, broadcasting, vectorisation, and ufuncs - how NumPy achieves C-speed from Python.03Pandas for MLPandas for machine learning - efficient data loading, feature engineering, pipelines, memory optimisation, and common ML preprocessing patterns.04SciPy for MLSciPy for machine learning - optimisation, sparse matrices, statistical distributions, signal processing, and distance metrics.05Matplotlib and SeabornProduction-grade visualisation for ML - diagnostic plots, training curves, feature importance, distribution analysis, and publication-quality figures.06Scikit-Learn PipelinesScikit-learn Pipeline, ColumnTransformer, custom transformers, feature unions, and production-ready ML workflows.07PyTorch FundamentalsPyTorch tensors, autograd, neural network modules, training loops, GPU acceleration, and production patterns for deep learning.08JAX and Functional MLJAX jit, grad, vmap, pmap - functional transformations for high-performance ML, XLA compilation, and NumPy-compatible ML research.
